Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes beyond the annotations by explaining the verdict types (proved/refuted/unknown), the soundness semantics of each method (structural/exhaustive/partial), and the caveats. It clarifies that 'unknown is never a pass' and that partial results are only sound for refutations. The annotations declare destructiveHint=true, and the description does not contradict this; it adds meaningful behavioral context about the verification guarantees.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but well-structured: it front-loads the core purpose, then explains verdict semantics, then method soundness, then caveats. Every sentence adds information. It could be slightly more concise, but the density is justified given the complexity of the verification semantics.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a verification tool with no output schema, the description does a good job explaining what the agent should expect: verdicts, methods, and caveats. It doesn't describe the exact response format, but the verdict/method/caveat structure is implied. The annotations cover the safety profile (destructiveHint=true), and the description covers the semantic guarantees. Minor gap: no explicit statement about what happens on invalid input or how to interpret the 'id' parameter beyond 'model id'.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents both parameters. The description adds context about what 'properties' means (the property kinds) and the default (bounded + deadlock-free), which is useful. However, it doesn't add syntax details beyond the schema's example, so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('verify') and resource ('declared properties of a stored model'), and enumerates the property kinds it handles. It distinguishes itself from siblings like sim_invariants and sim_diagnose by naming the exact property classes and verdict semantics.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly explains when to use the tool: to verify declared properties of a model. It does not explicitly name alternative tools for other verification tasks, but it provides enough context about the property kinds and verdict semantics that an agent can infer when this tool is appropriate. The caveats section also signals when results may be incomplete.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.